© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62415
    Prev
    Next
    INDEX
    Explanations

    gcd, agreement, music, bystander

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç¼Ī
    -0.07
    olta
    -0.07
    charge
    -0.07
    éĻĨ家
    -0.07
    éĻIJå®ļ
    -0.07
    _MARKER
    -0.07
    _limits
    -0.07
     Kha
    -0.07
    é²²é¹ı
    -0.06
     Roses
    -0.06
    POSITIVE LOGITS
    åľ¨è¿Ļ次
    0.08
    以å¾ħ
    0.07
    iece
    0.07
    neck
    0.07
    illis
    0.07
    dna
    0.07
    çļĦä¸Ģå¹´éĩĮ
    0.07
     hinweg
    0.07
    feit
    0.07
    _HOOK
    0.06
    Activations Density 0.002%

    No Known Activations